Semi-Automatic Logging with Sematic Annotation

We have developed a semi-automated system for use by postproduction professionals and archivists. Called SALSA (Semi-Automated Logging with Semantic Annotation) [1], the system also provides the foundation for future research in metadata extraction during ingest of archival media.

SALSA is a system that analyses movies in a way useful for post-production and archiving. It detects shot boundaries, parses camera moves, and provides an efficient way for users to insert and edit higher-level annotations. It is the practical result of our wider research in motion-picture analysis described under the heading Motion-Picture Parsing and Summarization. SALSA has no problem handling black-and-white footage, cartoons, or any other kind of source material.

SALSA is currently being developed into a product, and is undergoing evaluation by film editors and other motion-picture industry professionals.

The picture below is a reduced-resolution screenshot of SALSA. Thumbnails at the bottom show keyframes of shots extracted by ASAP; the left-hand text box contains automatically-extracted movement logging with the right-hand text box available for stenographic annotations. All the upper half of the window is given over to previewing and shot manipulation.

SALSA screen shot

[1] J W Mateer, J A Robinson. A Vision-Based Postproduction Tool for Footage Logging, Analysis and Annotation Journal of Graphical Models Vol 67, No 6, pp 565-583, Nov 2005.

 

Back to the Top